{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:11:13Z","timestamp":1784178673458,"version":"3.55.0"},"reference-count":363,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2015,9,1]],"date-time":"2015-09-01T00:00:00Z","timestamp":1441065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2015,9]]},"DOI":"10.1109\/taslp.2015.2438543","type":"journal-article","created":{"date-parts":[[2015,6,3]],"date-time":"2015-06-03T20:42:24Z","timestamp":1433364144000},"page":"1389-1420","source":"Crossref","is-referenced-by-count":82,"title":["Spoken Content Retrieval\u2014Beyond Cascading Speech Recognition with Text Retrieval"],"prefix":"10.1109","volume":"23","author":[{"given":"Lin-shan","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun-an","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref275","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-560","article-title":"Effects of query expansion for spoken document passage retrieval","author":"akiba","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref274","first-page":"85","article-title":"Document expansion using a side collection for monolingual and cross-language spoken document retrieval","author":"chi li","year":"2003","journal-title":"ISCA Workshop Multiling Spoken Doc Retrieval"},{"key":"ref363","article-title":"Graph-based re-ranking using acoustic feature similarity between search results for spoken term detection on low-resource languages","author":"lee","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref277","article-title":"Web page collection using automatic document segmentation for spoken document retrieval","author":"nishizaki","year":"2011","journal-title":"Proc APSIPA"},{"key":"ref362","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2010.04.005"},{"key":"ref276","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-559","article-title":"Language model expansion using webdata for spoken document retrieval","author":"masumura","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref361","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-1","article-title":"Still talking to machines (cognitively speaking)","author":"young","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163963"},{"key":"ref360","article-title":"Talking to machines (statistically speaking)","author":"young","year":"2002","journal-title":"Proc ICSLP"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1145\/502585.502654"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835546"},{"key":"ref273","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-265","article-title":"Cluster-based language model for spoken document retrieval using NMF-based document clustering","author":"hu","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref272","author":"rocchio","year":"1971","journal-title":"The SMART Retrieval System - Experiments in Automatic Document Processing"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101288"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/WI.2003.1241200"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/WIAMIS.2009.5031421"},{"key":"ref173","article-title":"Negative pseudo-relevance feedback in content-based video retrieval","author":"yan","year":"2003","journal-title":"Proc 11th ACM Int Conf Multimedia"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/89.544527"},{"key":"ref175","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1007\/3-540-45113-7_24","article-title":"Multimedia search with pseudo-relevance feedback","author":"yan","year":"2003","journal-title":"Proc Inter Con on Image and Video Retrieval"},{"key":"ref178","article-title":"A hybrid HMM\/DNN approach to keyword spotting of short words","volume":"13","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2248721"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390377"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/1645953.1646259"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638969"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853589"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2207989"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-619","article-title":"Sparse representation features for speech recognition","author":"sainath","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref359","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639326"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2208663"},{"key":"ref30","author":"povey","year":"2003","journal-title":"Discriminative training for large vocabulary speech recognition"},{"key":"ref357","doi-asserted-by":"crossref","DOI":"10.1145\/1102351.1102462","article-title":"Finite time bounds for sampling based fitted value iteration","author":"szepesv\ufffdri","year":"2005","journal-title":"Proc ICML"},{"key":"ref267","article-title":"A comparative study of utilizing topic models for information retrieval","author":"yi","year":"2009","journal-title":"Proc 31th Eur Conf IR Res Adv Inf Retrieval"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref358","doi-asserted-by":"publisher","DOI":"10.3115\/1614108.1614146"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277796"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2199112"},{"key":"ref355","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639301"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1145\/383952.383972"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2227738"},{"key":"ref356","doi-asserted-by":"publisher","DOI":"10.1109\/89.817450"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2244083"},{"key":"ref352","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.007"},{"key":"ref288","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-373","article-title":"Leveraging relevance cues for improved spoken document retrieval","author":"chen","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref351","volume":"42","author":"ruthven","year":"2008","journal-title":"Interactive Information Retrieval"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2208628"},{"key":"ref354","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.06.008"},{"key":"ref286","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-546","article-title":"Phonetic query expansion for spoken document retrieval","author":"mamou","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref353","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-564","article-title":"Interactive spoken content retrieval with different types of actions optimized by a Markov decision process","author":"wen","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424219"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289064"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.12.003"},{"key":"ref283","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-572","article-title":"Vocabulary independent discriminative term frequency estimation","author":"olsson","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref180","article-title":"Semi-supervised manifold learning approaches for spoken term verification","author":"norouzian","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref350","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2006.326811"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163966"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285469"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639282"},{"key":"ref280","article-title":"A statistical language modeling approach to lattice-based spoken document retrieval","author":"chia","year":"2007","journal-title":"Proc Joint Conf Empir Meth Nat Lang Process Comput Natural Lang Learn"},{"key":"ref184","author":"lee","year":"2012","journal-title":"Spoken content retrieval?relevance feedback graphs and semantics"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947640"},{"key":"ref182","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-554","article-title":"Open-vocabulary retrieval of spoken content with shorter\/longer queries considering word\/subword-based acoustic feature similarity","author":"lee","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291446"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1137\/S0036144503424786"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/153244303322533223"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495662"},{"key":"ref179","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-639","article-title":"Exploiting discriminative point process models for spoken term detection","author":"norouzian","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040782"},{"key":"ref348","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541884"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960682"},{"key":"ref349","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-115","article-title":"Efficient interactive retrieval of spoken documents with key terms ranked by reinforcement learning","author":"pan","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2197232"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372901"},{"key":"ref344","year":"0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2197156"},{"key":"ref345","article-title":"Rough?n?Ready: A meeting recorder and browser","author":"colbath","year":"1999","journal-title":"ACM Comput Surveys"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2207140"},{"key":"ref346","doi-asserted-by":"crossref","DOI":"10.1007\/11526346_1","article-title":"Lessons for the future from a decade of informedia video analysis research","author":"hauptmann","year":"2005","journal-title":"Proc Inter Con on Image and Video Retrieval"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref278","article-title":"Spoken document retrieval method combining query expansion with continuous syllable recognition for NTCIR-SpokenDoc","author":"tsuge","year":"2011","journal-title":"Proc 9th NTCIR Workshop Meeting"},{"key":"ref347","article-title":"Hierarchical topic organization and visual presentation of spoken documents using probabilistic latent semantic analysis (PLSA) for efficient retrieval\/browsing applications","author":"li","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1145\/1658377.1658379"},{"key":"ref50","year":"0"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707729"},{"key":"ref51","year":"0"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPA.2012.6310546"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430190"},{"key":"ref294","article-title":"The FIRE 2013question answering for the spoken web task","author":"oard","year":"2013","journal-title":"Proc FIRE"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394538"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639335"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2102592"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1145\/506218.506246"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947641"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163962"},{"key":"ref156","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-636","article-title":"A novel condence measure based on context consistency for spoken term detection","author":"li","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639337"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.10.002"},{"key":"ref152","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-263","article-title":"Contextual verification for open vocabulary spoken term detection","author":"schneider","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639283"},{"key":"ref151","article-title":"Discriminative keyword spotting","author":"keshet","year":"2007","journal-title":"Proc NOLISP"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2008.4777896"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2186805"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639281"},{"key":"ref148","article-title":"Discriminative spoken term detection with limited data","author":"prabhavalkar","year":"2012","journal-title":"Proc MLSLP"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960492"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/1220575.1220694"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.802541"},{"key":"ref58","article-title":"Text REtrieval Conf.","year":"0"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1002\/9781119992691"},{"key":"ref55","first-page":"1","author":"voorhees","year":"2000","journal-title":"Overview 8th Text Retrieval Conf (TREC-8)"},{"key":"ref54","article-title":"1998 trec-7 spoken document retrieval track overview and results","author":"garofolo","year":"1999","journal-title":"Proc 7th Text Retrieval Conf TREC-7"},{"key":"ref53","article-title":"Overview of the IR for spoken documents task in NTCIR-9 workshop","author":"akiba","year":"2011","journal-title":"Proc NTCIR-9 Workshop"},{"key":"ref52","year":"0"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639279"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148201"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076041"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2011.5972537"},{"key":"ref164","article-title":"A study on word detector design and knowledge-based pruning and rescoring","author":"ma","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.10.001"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424223"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424217"},{"key":"ref160","article-title":"Speech signal- and term-based feature contribution to hit\/false alarm classification in a spoken term detection system","author":"tejedor","year":"2010","journal-title":"Proc FALA"},{"key":"ref4","article-title":"Voice-based information retrieval?how far are we from the text-based information retrieval?","author":"lee","year":"2009","journal-title":"Proc ASRU"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/1500000020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1511824"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1511823"},{"key":"ref159","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-264","article-title":"Augmented set of features for confidence estimation in spoken term detection","author":"tejedor","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390397"},{"key":"ref7","first-page":"1","article-title":"Recent developments in spoken term detection: A survey","author":"mandal","year":"2013","journal-title":"Int J Speech Technol"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.918411"},{"key":"ref157","article-title":"Contextual information improves oov detection in speech","author":"parada","year":"2010","journal-title":"Proc Human Lang Technol Annu Conf North Amer Chap Assoc Comput Linguist"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494966"},{"key":"ref9","first-page":"129","article-title":"Lattice-based search for spoken utterance retrieval","author":"saraclar","year":"2004","journal-title":"Proc HLT-NAACL"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707728"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853583"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/281250.281253"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854531"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707731"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639278"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707770"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855126"},{"key":"ref320","article-title":"A comparative study on speech summarization of broadcast news and lecture speech","author":"zhang","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref321","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-614","article-title":"Supervised spoken document summarization jointly considering utterance importance and redundancy by structured support vector machine","author":"lee","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2006.326813"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660178"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148183"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367166"},{"key":"ref76","article-title":"An experimental study of an audio indexing system for the web","author":"logan","year":"2000","journal-title":"Proc ICSLP"},{"key":"ref318","first-page":"941","article-title":"Improved spoken document summarization using probabilistic latent semantic analysis (PLSA)","author":"kong","year":"2006","journal-title":"Proc ICASSP"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289059"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518841"},{"key":"ref316","first-page":"4985","article-title":"Using corpus and knowledge-based similarity measure in maximum marginal relevance for meeting summarization","author":"xie","year":"2008","journal-title":"Proc ICASSP"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3115\/1220835.1220888"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289061"},{"key":"ref75","first-page":"629","article-title":"Towards spoken-document retrieval for the enterprise: Approximate word-lattice indexing with text indexers","author":"seide","year":"2007","journal-title":"Proc ASRU"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2030951"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828699"},{"key":"ref78","article-title":"Subword-based position specific posterior lattices (S-PSPL) for indexing speech information","author":"pan","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref312","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-605","article-title":"Class lecture summarization taking into account consecutiveness of important sentences","author":"fujii","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.854429"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2255279"},{"key":"ref319","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-456","article-title":"Clusterrank: A graph based method for meeting summarization","author":"garg","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960697"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518842"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947645"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700850"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.872615"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1145\/1482343.1482346"},{"key":"ref64","article-title":"Search in speech for public security and defense","author":"cernocky","year":"2007","journal-title":"Proc Process Applicat Public Security Forensics (SAFE?07)"},{"key":"ref304","author":"maskey","year":"2008","journal-title":"Automatic broadcast news speech summarization"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2008.4777893"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2253098"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/1626307.1626314"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494956"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134087"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424256"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373341"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2163512"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960494"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1002\/9781119992691"},{"key":"ref302","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1109\/TASLP.2014.2310993","article-title":"Spoken knowledge organization by semantic structuring and a prototype course lecture system for personalized learning","volume":"22","author":"lee","year":"2014","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373302"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.04.007"},{"key":"ref197","article-title":"Query by example search on speech at mediaeval 2014","author":"anguera","year":"2014","journal-title":"Proc Mediaeval Workshop"},{"key":"ref198","year":"0"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.12.004"},{"key":"ref193","year":"0"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289083"},{"key":"ref195","article-title":"The spoken web search task","author":"metze","year":"2012","journal-title":"Proc Mediaeval Workshop"},{"key":"ref196","article-title":"The spoken web search task","author":"anguera","year":"2013","journal-title":"Proc Mediaeval Workshop"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707766"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459378"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2164531"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2008.06.004"},{"key":"ref93","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1109\/TASL.2009.2037404","article-title":"Performance analysis for lattice-based speech indexing approaches using words and subword units","volume":"18","author":"pan","year":"2010","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref192","article-title":"Improved speech summarization and spoken term detection with graphical analysis of utterance similarities","author":"lee","year":"2011","journal-title":"Proc APSIPA"},{"key":"ref92","first-page":"677","article-title":"Analytical comparison between position specific posterior lattices and confusion networks based on words and subword units for spoken document indexing","author":"pan","year":"2007","journal-title":"Proc ASRU"},{"key":"ref342","doi-asserted-by":"publisher","DOI":"10.1109\/72.846729"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494968"},{"key":"ref343","doi-asserted-by":"crossref","first-page":"149","DOI":"10.3233\/IDA-2000-4205","article-title":"ProbMap?a probabilistic approach for mapping large document collections","volume":"4","author":"hofmann","year":"2000","journal-title":"Intell Data Anal"},{"key":"ref90","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-481","article-title":"CRF-based stochastic pronunciation modeling for out-of-vocabulary spoken term detection","author":"wang","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref340","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700862"},{"key":"ref341","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289053"},{"key":"ref336","first-page":"181","article-title":"Automatic keyword extraction for the meeting corpus using supervised approach and bigram expansion","author":"liu","year":"2008","journal-title":"Proc SLT"},{"key":"ref335","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1572113"},{"key":"ref334","article-title":"Keyphrase extraction for summarization purposes: The LAKE system at DUC-2004","author":"d?avanzo","year":"2004","journal-title":"Proc Doc Understand Conf"},{"key":"ref333","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2008.4777866"},{"key":"ref98","article-title":"BBN presentation at IARPA babel PI meeting","year":"2012"},{"key":"ref339","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-369","article-title":"Latent topic modeling for audio corpus summarization","author":"hazen","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854973"},{"key":"ref338","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620845"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.3115\/1620853.1620928"},{"key":"ref337","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052119"},{"key":"ref97","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-498","article-title":"White listing and score normalization for keyword spotting of noisy speech","author":"zhang","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277849"},{"key":"ref81","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-565","article-title":"Reducing the effect of OOV query words by using morph-based spoken document retrieval","author":"turunen","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref84","article-title":"An integration method of retrieval results using plural subword models for vocabulary-free spoken document retrieval","author":"itoh","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518773"},{"key":"ref330","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373302"},{"key":"ref80","article-title":"A phonetic search approach to the 2006NIST spoken term detection evaluation","author":"wallace","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639295"},{"key":"ref332","doi-asserted-by":"publisher","DOI":"10.3115\/1690219.1690223"},{"key":"ref89","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-610","article-title":"Stochastic pronunciation modelling for spoken term detection","author":"wang","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref323","article-title":"Supervised spoken document summarization based on structured support vector machine with utterance clusters as hidden variables","author":"shiang","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639293"},{"key":"ref325","article-title":"Using confusion networks for speech summarization","author":"xie","year":"2010","journal-title":"Proc Human Lang Technol Annu Conf North Amer Chap Assoc Comput Linguist"},{"key":"ref324","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-457","article-title":"Leveraging sentence weights in a concept-based optimization framework for extractive meeting summarization","author":"xie","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660179"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415298"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518771"},{"key":"ref326","article-title":"Minimizing word error rate in textual summaries of spoken language","author":"zechner","year":"2000","journal-title":"Proc 1st North Amer Chap Assoc Comput Linguist Conf"},{"key":"ref87","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-558","article-title":"Towards using hybrid word and fragment units for vocabulary independent LVCSR systems","author":"rastrow","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref329","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-66","article-title":"Comparing lexical, acoustic\/prosodic, structural and discourse features for speech summarization","author":"maskey","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref88","article-title":"Hybrid word-subword decoding for spoken term detection","author":"szoke","year":"2008","journal-title":"Proc 31st Annu Int ACM SIGIR Conf Res Develop Inf Retrieval"},{"key":"ref328","doi-asserted-by":"crossref","DOI":"10.21437\/SpeechProsody.2004-138","article-title":"Improvement of speech summarization using prosodic information","author":"inoue","year":"2004","journal-title":"Proc Speech Prosody"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639277"},{"key":"ref100","first-page":"505","article-title":"Combining multiple subword representations for open-vocabulary spoken document retrieval","author":"lee","year":"2005","journal-title":"Proc ICASSP"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495637"},{"key":"ref203","first-page":"398","article-title":"Unsupervised spoken keyword spotting via segmental DTW on gaussian posteriorgrams","author":"zhang","year":"2010","journal-title":"Proc ICASSP"},{"key":"ref204","author":"chan","year":"2012","journal-title":"Unsupervised spoken term detection with spoken queries"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref207","article-title":"ELiRF at MediaEval 2014: Query by example search on speech task (QUESST)","author":"calvo","year":"2014","journal-title":"Proc MediaEval"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372889"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2013.6607546"},{"key":"ref206","article-title":"BUT SWS 2013- massive parallel approach","author":"szoke","year":"2013","journal-title":"Proc MediaEval"},{"key":"ref211","article-title":"CUHK system for the spoken web search task at MediaEval 2012","author":"wang","year":"2012","journal-title":"Proc MediaEval"},{"key":"ref210","article-title":"CUHK system for QUESST task of MediaEval 2014","author":"wang","year":"2014","journal-title":"Proc MediaEval"},{"key":"ref212","year":"0"},{"key":"ref213","first-page":"7849","article-title":"Calibration and fusion of query-by-example systems?BUT SWS 2013","author":"szoke","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref214","article-title":"IIIT-H system for MediaEval 2014QUESST","author":"kesiraju","year":"2014","journal-title":"Proc MediaEval"},{"key":"ref215","article-title":"IIIT-H SWS 2013: Gaussian posteriorgrams of bottle-neck features for query-by-example spoken term detection","author":"mantena","year":"2013","journal-title":"Proc MediaEval"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289081"},{"key":"ref217","article-title":"A nonparametric Bayesian approach to acoustic model discovery","author":"lee","year":"2012","journal-title":"Proc ACL"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289082"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2238931"},{"key":"ref220","article-title":"Intrinsic spectral analysis based on temporal context features for query by example spoken term detection","author":"yang","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref222","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-609","article-title":"Online unsupervised pattern discovery in speech using parallelization","author":"gajjar","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref221","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-304","article-title":"Rapid evaluation of speech representations for spoken term discovery","author":"carlin","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref228","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-355","article-title":"A piecewise aggregate approximation lower-bound estimate for posteriorgram-based dynamic time warping","author":"zhang","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947644"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1016\/B978-155860869-6\/50043-3"},{"key":"ref225","first-page":"3989","article-title":"Unsupervised optimal phoneme segmentation: Objectives, algorithm and comparisons","author":"qiao","year":"2008","journal-title":"Proc ICASSP"},{"key":"ref224","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-262","article-title":"Unsupervised spoken term detection with spoken queries using segment-based dynamic time warping","author":"chan","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289085"},{"key":"ref127","article-title":"Low-resource open vocabulary keyword search using point process models","author":"liu","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855130"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2021307"},{"key":"ref124","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-487","article-title":"A study on using word-level HMMs to improve ASR performance over state-of-the-art phone-level acoustic modeling for LVCSR","author":"chen","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2196514"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888903000638"},{"key":"ref130","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-400","article-title":"Improved spoken term detection by discriminative training of acoustic models based on user relevance feedback","author":"lee","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref133","article-title":"Optimizing search engines using clickthrough data","author":"thorsten","year":"2002","journal-title":"Proc KDD"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2008366"},{"key":"ref131","article-title":"A framework integrating different relevance feedback scenarios and approaches for spoken term detection","author":"lee","year":"2012","journal-title":"Proc SLT"},{"key":"ref132","article-title":"Improving retrieval performance by user feedback: A new framework for spoken term detection","author":"lee","year":"2010","journal-title":"Proc ICASSP"},{"key":"ref232","article-title":"Information retrieval-based dynamic time warping","author":"anguera","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref233","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-184","article-title":"Towards unsupervised training of speaker independent acoustic models","author":"jansen","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref230","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-566","article-title":"Indexing raw acoustic feature for scalable zero resource search","author":"jansen","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1145\/509961.509965"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196629"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289077"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2007.911723"},{"key":"ref234","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-483","article-title":"Towards spoken term discovery at scale with zero resources","author":"jansen","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref237","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-244","article-title":"Word discovery with beta process factor analysis","author":"vanhainen","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref236","article-title":"An iterative approach to model merging for speech pattern discovery","author":"wang","year":"2011","journal-title":"Proc APSIPA"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936713"},{"key":"ref135","article-title":"Strategies for high accuracy keyword detection in noisy channels","author":"mandal","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707774"},{"key":"ref137","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-637","article-title":"Discriminatively trained phoneme confusion model for keyword spotting","author":"karanasou","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494969"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2096215"},{"key":"ref141","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-567","article-title":"Spoken document retrieval by translating recognition candidates into correct transcriptions","author":"tomoyosi akiba","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415151"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960726"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430191"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.917992"},{"key":"ref145","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-608","article-title":"Merging search spaces for subword spoken term detection","author":"mertens","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119992691"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639241"},{"key":"ref242","article-title":"GTTS systems for the SWS task at MediaEval 2013","author":"rodrguez-fuentes","year":"2013","journal-title":"Proc MediaEval"},{"key":"ref243","article-title":"GTTS-EHU systems for QUESST at MediaEval 2014","author":"rodriguez-fuentes","year":"2014","journal-title":"Proc MediaEval"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639333"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639239"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947338"},{"key":"ref247","article-title":"The SPL-IT query by example search on speech system for MediaEval 2014","author":"proena","year":"2014","journal-title":"Proc MediaEval"},{"key":"ref246","article-title":"SpeeD@MediaEval 2014: Spoken term detection with robust multilingual phone recognition","author":"buzo","year":"2014","journal-title":"Proc MediaEval"},{"key":"ref245","article-title":"The NNI query-by-example system for MediaEval 2014","author":"yang","year":"2014","journal-title":"Proc MediaEval"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2248714"},{"key":"ref109","author":"larson","year":"2009","journal-title":"Advances in Information Retrieval"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758059"},{"key":"ref107","article-title":"Evaluating ASR output for information retrieval","author":"van der werff","year":"2007","journal-title":"Proc SSCS"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289102"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2236631"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960728"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494981"},{"key":"ref102","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-260","article-title":"Combining Chinese spoken term detection systems via side-information conditioned linear logistic regression","author":"meng","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/1631127.1631132"},{"key":"ref112","article-title":"Improved measures for predicting the usefulness of recognition lattices in ranked utterance retrieval","author":"olsson","year":"2007","journal-title":"Proc SSCS"},{"key":"ref110","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-563","article-title":"Towards vocabulary-independent speech indexing for large-scale repositories","author":"shao","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639334"},{"key":"ref251","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-561","article-title":"Unsupervised hidden Markov modeling of spoken queries for spoken term detection without speech recognition","author":"chan","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1145\/361219.361220"},{"key":"ref252","author":"baeza-yates","year":"1999","journal-title":"Modern Information Retrieval"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855121"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291008"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1561\/1500000008"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219895"},{"key":"ref11","article-title":"The SRI\/OGI 2006spoken term detection system","author":"vergyri","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1145\/383952.384019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277847"},{"key":"ref13","article-title":"Rapid and accurate spoken term detection","author":"miller","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref14","author":"ng","year":"2000","journal-title":"Subword-Based Approaches for Spoken Document Retrieval"},{"key":"ref15","author":"garofolo","year":"2000","journal-title":"The TREC Spoken Document Retrieval Track A Success Story"},{"key":"ref16","year":"0"},{"key":"ref118","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-172","article-title":"Discriminative training using non-uniform criteria for keyword spotting on spontaneous speech","author":"weng","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1631127.1631133"},{"key":"ref117","first-page":"278","article-title":"Automatic speech recognition based on weighted minimum classification error (W-MCE) training method","author":"fu","year":"2007","journal-title":"Proc ASRU"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960723"},{"key":"ref19","article-title":"Recent progress in the MIT spoken lecture processing project","author":"glass","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639011"},{"key":"ref114","first-page":"105","article-title":"Minimum phone error and i-smoothing for improved discriminative training","author":"povey","year":"2002","journal-title":"Proc ICASSP"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/89.568732"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.926652"},{"key":"ref115","article-title":"Sequence-discriminative training of deep neural networks","author":"vesely","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2165279"},{"key":"ref121","article-title":"A keyword-boosted sMBR criterion to enhance keyword search performance in deep neural network based acoustic modeling","author":"chen","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref122","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-560","article-title":"Robust event detection from spoken content in consumer domain videos","author":"tsakalidis","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref123","article-title":"A resource-dependent approach to word modeling for keyword spotting","author":"chen","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref260","article-title":"Probabilistic latent semantic analysis","author":"hofmann","year":"1999","journal-title":"Proc Uncertainty in Artif Intell (UAI?99)"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.3.4-5.993"},{"key":"ref262","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by non-negative matrix factorization","volume":"401","author":"lee","year":"1999","journal-title":"Nature"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312645"},{"key":"ref264","article-title":"Document expansion versus query expansion for ad-hoc retrieval","author":"billerbeck","year":"2005","journal-title":"Proc 10th Australasian Doc Comput Symp"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148204"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010008"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7118277\/07114229.pdf?arnumber=7114229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T08:49:42Z","timestamp":1748422182000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7114229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9]]},"references-count":363,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2015.2438543","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,9]]}}}